1 files changed, 133 insertions, 73 deletions

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 168f08507004..321d8ffbab6e 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -8,7 +8,6 @@
 #include <linux/fs.h>
 #include <linux/f2fs_fs.h>
 #include <linux/stat.h>
-#include <linux/buffer_head.h>
 #include <linux/writeback.h>
 #include <linux/blkdev.h>
 #include <linux/falloc.h>
@@ -54,7 +53,7 @@ static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf)
 
 static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 {
-	struct page *page = vmf->page;
+	struct folio *folio = page_folio(vmf->page);
 	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct dnode_of_data dn;
@@ -86,7 +85,7 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 	if (f2fs_compressed_file(inode)) {
-		int ret = f2fs_is_compressed_cluster(inode, page->index);
+		int ret = f2fs_is_compressed_cluster(inode, folio->index);
 
 		if (ret < 0) {
 			err = ret;
@@ -106,11 +105,11 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 
 	file_update_time(vmf->vma->vm_file);
 	filemap_invalidate_lock_shared(inode->i_mapping);
-	lock_page(page);
-	if (unlikely(page->mapping != inode->i_mapping ||
-			page_offset(page) > i_size_read(inode) ||
-			!PageUptodate(page))) {
-		unlock_page(page);
+	folio_lock(folio);
+	if (unlikely(folio->mapping != inode->i_mapping ||
+			folio_pos(folio) > i_size_read(inode) ||
+			!folio_test_uptodate(folio))) {
+		folio_unlock(folio);
 		err = -EFAULT;
 		goto out_sem;
 	}
@@ -118,9 +117,9 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
 	if (need_alloc) {
 		/* block allocation */
-		err = f2fs_get_block_locked(&dn, page->index);
+		err = f2fs_get_block_locked(&dn, folio->index);
 	} else {
-		err = f2fs_get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
+		err = f2fs_get_dnode_of_data(&dn, folio->index, LOOKUP_NODE);
 		f2fs_put_dnode(&dn);
 		if (f2fs_is_pinned_file(inode) &&
 		    !__is_valid_data_blkaddr(dn.data_blkaddr))
@@ -128,11 +127,11 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 	}
 
 	if (err) {
-		unlock_page(page);
+		folio_unlock(folio);
 		goto out_sem;
 	}
 
-	f2fs_wait_on_page_writeback(page, DATA, false, true);
+	f2fs_wait_on_page_writeback(folio_page(folio, 0), DATA, false, true);
 
 	/* wait for GCed page writeback via META_MAPPING */
 	f2fs_wait_on_block_writeback(inode, dn.data_blkaddr);
@@ -140,18 +139,18 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 	/*
 	 * check to see if the page is mapped already (no holes)
 	 */
-	if (PageMappedToDisk(page))
+	if (folio_test_mappedtodisk(folio))
 		goto out_sem;
 
 	/* page is wholly or partially inside EOF */
-	if (((loff_t)(page->index + 1) << PAGE_SHIFT) >
+	if (((loff_t)(folio->index + 1) << PAGE_SHIFT) >
 						i_size_read(inode)) {
 		loff_t offset;
 
 		offset = i_size_read(inode) & ~PAGE_MASK;
-		zero_user_segment(page, offset, PAGE_SIZE);
+		folio_zero_segment(folio, offset, folio_size(folio));
 	}
-	set_page_dirty(page);
+	folio_mark_dirty(folio);
 
 	f2fs_update_iostat(sbi, inode, APP_MAPPED_IO, F2FS_BLKSIZE);
 	f2fs_update_time(sbi, REQ_TIME);
@@ -163,7 +162,7 @@ out_sem:
 out:
 	ret = vmf_fs_error(err);
 
-	trace_f2fs_vm_page_mkwrite(inode, page->index, vmf->vma->vm_flags, ret);
+	trace_f2fs_vm_page_mkwrite(inode, folio->index, vmf->vma->vm_flags, ret);
 	return ret;
 }
 
@@ -218,6 +217,9 @@ static inline enum cp_reason_type need_do_checkpoint(struct inode *inode)
 		f2fs_exist_written_data(sbi, F2FS_I(inode)->i_pino,
 							TRANS_DIR_INO))
 		cp_reason = CP_RECOVER_DIR;
+	else if (f2fs_exist_written_data(sbi, F2FS_I(inode)->i_pino,
+							XATTR_DIR_INO))
+		cp_reason = CP_XATTR_DIR;
 
 	return cp_reason;
 }
@@ -373,8 +375,7 @@ sync_nodes:
 	f2fs_remove_ino_entry(sbi, ino, APPEND_INO);
 	clear_inode_flag(inode, FI_APPEND_WRITE);
 flush_out:
-	if ((!atomic && F2FS_OPTION(sbi).fsync_mode != FSYNC_MODE_NOBARRIER) ||
-	    (atomic && !test_opt(sbi, NOBARRIER) && f2fs_sb_has_blkzoned(sbi)))
+	if (!atomic && F2FS_OPTION(sbi).fsync_mode != FSYNC_MODE_NOBARRIER)
 		ret = f2fs_issue_flush(sbi, inode->i_ino);
 	if (!ret) {
 		f2fs_remove_ino_entry(sbi, ino, UPDATE_INO);
@@ -431,7 +432,7 @@ static bool __found_offset(struct address_space *mapping,
 static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
 {
 	struct inode *inode = file->f_mapping->host;
-	loff_t maxbytes = inode->i_sb->s_maxbytes;
+	loff_t maxbytes = F2FS_BLK_TO_BYTES(max_file_blocks(inode));
 	struct dnode_of_data dn;
 	pgoff_t pgofs, end_offset;
 	loff_t data_ofs = offset;
@@ -513,10 +514,7 @@ fail:
 static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct inode *inode = file->f_mapping->host;
-	loff_t maxbytes = inode->i_sb->s_maxbytes;
-
-	if (f2fs_compressed_file(inode))
-		maxbytes = max_file_blocks(inode) << F2FS_BLKSIZE_BITS;
+	loff_t maxbytes = F2FS_BLK_TO_BYTES(max_file_blocks(inode));
 
 	switch (whence) {
 	case SEEK_SET:
@@ -1052,6 +1050,13 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 				return err;
 		}
 
+		/*
+		 * wait for inflight dio, blocks should be removed after
+		 * IO completion.
+		 */
+		if (attr->ia_size < old_size)
+			inode_dio_wait(inode);
+
 		f2fs_down_write(&fi->i_gc_rwsem[WRITE]);
 		filemap_invalidate_lock(inode->i_mapping);
 
@@ -1888,6 +1893,12 @@ static long f2fs_fallocate(struct file *file, int mode,
 	if (ret)
 		goto out;
 
+	/*
+	 * wait for inflight dio, blocks should be removed after IO
+	 * completion.
+	 */
+	inode_dio_wait(inode);
+
 	if (mode & FALLOC_FL_PUNCH_HOLE) {
 		if (offset >= inode->i_size)
 			goto out;
@@ -2116,10 +2127,12 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
 	struct mnt_idmap *idmap = file_mnt_idmap(filp);
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct inode *pinode;
 	loff_t isize;
 	int ret;
 
+	if (!(filp->f_mode & FMODE_WRITE))
+		return -EBADF;
+
 	if (!inode_owner_or_capable(idmap, inode))
 		return -EACCES;
 
@@ -2149,6 +2162,7 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
 		goto out;
 
 	f2fs_down_write(&fi->i_gc_rwsem[WRITE]);
+	f2fs_down_write(&fi->i_gc_rwsem[READ]);
 
 	/*
 	 * Should wait end_io to count F2FS_WB_CP_DATA correctly by
@@ -2158,27 +2172,18 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
 		f2fs_warn(sbi, "Unexpected flush for atomic writes: ino=%lu, npages=%u",
 			  inode->i_ino, get_dirty_pages(inode));
 	ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX);
-	if (ret) {
-		f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
-		goto out;
-	}
+	if (ret)
+		goto out_unlock;
 
 	/* Check if the inode already has a COW inode */
 	if (fi->cow_inode == NULL) {
 		/* Create a COW inode for atomic write */
-		pinode = f2fs_iget(inode->i_sb, fi->i_pino);
-		if (IS_ERR(pinode)) {
-			f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
-			ret = PTR_ERR(pinode);
-			goto out;
-		}
+		struct dentry *dentry = file_dentry(filp);
+		struct inode *dir = d_inode(dentry->d_parent);
 
-		ret = f2fs_get_tmpfile(idmap, pinode, &fi->cow_inode);
-		iput(pinode);
-		if (ret) {
-			f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
-			goto out;
-		}
+		ret = f2fs_get_tmpfile(idmap, dir, &fi->cow_inode);
+		if (ret)
+			goto out_unlock;
 
 		set_inode_flag(fi->cow_inode, FI_COW_FILE);
 		clear_inode_flag(fi->cow_inode, FI_INLINE_DATA);
@@ -2187,11 +2192,13 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
 		F2FS_I(fi->cow_inode)->atomic_inode = inode;
 	} else {
 		/* Reuse the already created COW inode */
+		f2fs_bug_on(sbi, get_dirty_pages(fi->cow_inode));
+
+		invalidate_mapping_pages(fi->cow_inode->i_mapping, 0, -1);
+
 		ret = f2fs_do_truncate_blocks(fi->cow_inode, 0, true);
-		if (ret) {
-			f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
-			goto out;
-		}
+		if (ret)
+			goto out_unlock;
 	}
 
 	f2fs_write_inode(inode, NULL);
@@ -2210,7 +2217,11 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
 	}
 	f2fs_i_size_write(fi->cow_inode, isize);
 
+out_unlock:
+	f2fs_up_write(&fi->i_gc_rwsem[READ]);
 	f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
+	if (ret)
+		goto out;
 
 	f2fs_update_time(sbi, REQ_TIME);
 	fi->atomic_write_task = current;
@@ -2228,6 +2239,9 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
 	struct mnt_idmap *idmap = file_mnt_idmap(filp);
 	int ret;
 
+	if (!(filp->f_mode & FMODE_WRITE))
+		return -EBADF;
+
 	if (!inode_owner_or_capable(idmap, inode))
 		return -EACCES;
 
@@ -2260,6 +2274,9 @@ static int f2fs_ioc_abort_atomic_write(struct file *filp)
 	struct mnt_idmap *idmap = file_mnt_idmap(filp);
 	int ret;
 
+	if (!(filp->f_mode & FMODE_WRITE))
+		return -EBADF;
+
 	if (!inode_owner_or_capable(idmap, inode))
 		return -EACCES;
 
@@ -2279,7 +2296,7 @@ static int f2fs_ioc_abort_atomic_write(struct file *filp)
 }
 
 int f2fs_do_shutdown(struct f2fs_sb_info *sbi, unsigned int flag,
-							bool readonly)
+						bool readonly, bool need_lock)
 {
 	struct super_block *sb = sbi->sb;
 	int ret = 0;
@@ -2326,12 +2343,19 @@ int f2fs_do_shutdown(struct f2fs_sb_info *sbi, unsigned int flag,
 	if (readonly)
 		goto out;
 
+	/* grab sb->s_umount to avoid racing w/ remount() */
+	if (need_lock)
+		down_read(&sbi->sb->s_umount);
+
 	f2fs_stop_gc_thread(sbi);
 	f2fs_stop_discard_thread(sbi);
 
 	f2fs_drop_discard_cmd(sbi);
 	clear_opt(sbi, DISCARD);
 
+	if (need_lock)
+		up_read(&sbi->sb->s_umount);
+
 	f2fs_update_time(sbi, REQ_TIME);
 out:
 
@@ -2368,7 +2392,7 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
 		}
 	}
 
-	ret = f2fs_do_shutdown(sbi, in, readonly);
+	ret = f2fs_do_shutdown(sbi, in, readonly, true);
 
 	if (need_drop)
 		mnt_drop_write_file(filp);
@@ -2686,7 +2710,8 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
 				(range->start + range->len) >> PAGE_SHIFT,
 				DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE));
 
-	if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) {
+	if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED) ||
+		f2fs_is_atomic_file(inode)) {
 		err = -EINVAL;
 		goto unlock_out;
 	}
@@ -2710,7 +2735,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
 	 * block addresses are continuous.
 	 */
 	if (f2fs_lookup_read_extent_cache(inode, pg_start, &ei)) {
-		if (ei.fofs + ei.len >= pg_end)
+		if ((pgoff_t)ei.fofs + ei.len >= pg_end)
 			goto out;
 	}
 
@@ -2793,6 +2818,8 @@ do_map:
 				goto clear_out;
 			}
 
+			f2fs_wait_on_page_writeback(page, DATA, true, true);
+
 			set_page_dirty(page);
 			set_page_private_gcing(page);
 			f2fs_put_page(page, 1);
@@ -2917,6 +2944,11 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
 		goto out_unlock;
 	}
 
+	if (f2fs_is_atomic_file(src) || f2fs_is_atomic_file(dst)) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
 	ret = -EINVAL;
 	if (pos_in + len > src->i_size || pos_in + len < pos_in)
 		goto out_unlock;
@@ -2968,9 +3000,9 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
 	}
 
 	f2fs_lock_op(sbi);
-	ret = __exchange_data_block(src, dst, pos_in >> F2FS_BLKSIZE_BITS,
-				pos_out >> F2FS_BLKSIZE_BITS,
-				len >> F2FS_BLKSIZE_BITS, false);
+	ret = __exchange_data_block(src, dst, F2FS_BYTES_TO_BLK(pos_in),
+				F2FS_BYTES_TO_BLK(pos_out),
+				F2FS_BYTES_TO_BLK(len), false);
 
 	if (!ret) {
 		if (dst_max_i_size)
@@ -3014,10 +3046,10 @@ static int __f2fs_ioc_move_range(struct file *filp,
 		return -EBADF;
 
 	dst = fdget(range->dst_fd);
-	if (!dst.file)
+	if (!fd_file(dst))
 		return -EBADF;
 
-	if (!(dst.file->f_mode & FMODE_WRITE)) {
+	if (!(fd_file(dst)->f_mode & FMODE_WRITE)) {
 		err = -EBADF;
 		goto err_out;
 	}
@@ -3026,7 +3058,7 @@ static int __f2fs_ioc_move_range(struct file *filp,
 	if (err)
 		goto err_out;
 
-	err = f2fs_move_file_range(filp, range->pos_in, dst.file,
+	err = f2fs_move_file_range(filp, range->pos_in, fd_file(dst),
 					range->pos_out, range->len);
 
 	mnt_drop_write_file(filp);
@@ -3300,6 +3332,11 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg)
 
 	inode_lock(inode);
 
+	if (f2fs_is_atomic_file(inode)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	if (!pin) {
 		clear_inode_flag(inode, FI_PIN_FILE);
 		f2fs_i_gc_failures_write(inode, 0);
@@ -4193,6 +4230,8 @@ static int redirty_blocks(struct inode *inode, pgoff_t page_idx, int len)
 		/* It will never fail, when page has pinned above */
 		f2fs_bug_on(F2FS_I_SB(inode), !page);
 
+		f2fs_wait_on_page_writeback(page, DATA, true, true);
+
 		set_page_dirty(page);
 		set_page_private_gcing(page);
 		f2fs_put_page(page, 1);
@@ -4207,9 +4246,8 @@ static int f2fs_ioc_decompress_file(struct file *filp)
 	struct inode *inode = file_inode(filp);
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct f2fs_inode_info *fi = F2FS_I(inode);
-	pgoff_t page_idx = 0, last_idx;
-	int cluster_size = fi->i_cluster_size;
-	int count, ret;
+	pgoff_t page_idx = 0, last_idx, cluster_idx;
+	int ret;
 
 	if (!f2fs_sb_has_compression(sbi) ||
 			F2FS_OPTION(sbi).compress_mode != COMPR_MODE_USER)
@@ -4244,10 +4282,15 @@ static int f2fs_ioc_decompress_file(struct file *filp)
 		goto out;
 
 	last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
+	last_idx >>= fi->i_log_cluster_size;
 
-	count = last_idx - page_idx;
-	while (count && count >= cluster_size) {
-		ret = redirty_blocks(inode, page_idx, cluster_size);
+	for (cluster_idx = 0; cluster_idx < last_idx; cluster_idx++) {
+		page_idx = cluster_idx << fi->i_log_cluster_size;
+
+		if (!f2fs_is_compressed_cluster(inode, page_idx))
+			continue;
+
+		ret = redirty_blocks(inode, page_idx, fi->i_cluster_size);
 		if (ret < 0)
 			break;
 
@@ -4257,9 +4300,6 @@ static int f2fs_ioc_decompress_file(struct file *filp)
 				break;
 		}
 
-		count -= cluster_size;
-		page_idx += cluster_size;
-
 		cond_resched();
 		if (fatal_signal_pending(current)) {
 			ret = -EINTR;
@@ -4286,9 +4326,9 @@ static int f2fs_ioc_compress_file(struct file *filp)
 {
 	struct inode *inode = file_inode(filp);
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	pgoff_t page_idx = 0, last_idx;
-	int cluster_size = F2FS_I(inode)->i_cluster_size;
-	int count, ret;
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+	pgoff_t page_idx = 0, last_idx, cluster_idx;
+	int ret;
 
 	if (!f2fs_sb_has_compression(sbi) ||
 			F2FS_OPTION(sbi).compress_mode != COMPR_MODE_USER)
@@ -4322,10 +4362,15 @@ static int f2fs_ioc_compress_file(struct file *filp)
 	set_inode_flag(inode, FI_ENABLE_COMPRESS);
 
 	last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
+	last_idx >>= fi->i_log_cluster_size;
+
+	for (cluster_idx = 0; cluster_idx < last_idx; cluster_idx++) {
+		page_idx = cluster_idx << fi->i_log_cluster_size;
+
+		if (f2fs_is_sparse_cluster(inode, page_idx))
+			continue;
 
-	count = last_idx - page_idx;
-	while (count && count >= cluster_size) {
-		ret = redirty_blocks(inode, page_idx, cluster_size);
+		ret = redirty_blocks(inode, page_idx, fi->i_cluster_size);
 		if (ret < 0)
 			break;
 
@@ -4335,9 +4380,6 @@ static int f2fs_ioc_compress_file(struct file *filp)
 				break;
 		}
 
-		count -= cluster_size;
-		page_idx += cluster_size;
-
 		cond_resched();
 		if (fatal_signal_pending(current)) {
 			ret = -EINTR;
@@ -4538,6 +4580,13 @@ static ssize_t f2fs_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		f2fs_down_read(&fi->i_gc_rwsem[READ]);
 	}
 
+	/* dio is not compatible w/ atomic file */
+	if (f2fs_is_atomic_file(inode)) {
+		f2fs_up_read(&fi->i_gc_rwsem[READ]);
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+
 	/*
 	 * We have to use __iomap_dio_rw() and iomap_dio_complete() instead of
 	 * the higher-level function iomap_dio_rw() in order to ensure that the
@@ -4597,6 +4646,11 @@ static ssize_t f2fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		f2fs_trace_rw_file_path(iocb->ki_filp, iocb->ki_pos,
 					iov_iter_count(to), READ);
 
+	/* In LFS mode, if there is inflight dio, wait for its completion */
+	if (f2fs_lfs_mode(F2FS_I_SB(inode)) &&
+	    get_pages(F2FS_I_SB(inode), F2FS_DIO_WRITE))
+		inode_dio_wait(inode);
+
 	if (f2fs_should_use_dio(inode, iocb, to)) {
 		ret = f2fs_dio_read_iter(iocb, to);
 	} else {
@@ -4949,6 +5003,12 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	/* Determine whether we will do a direct write or a buffered write. */
 	dio = f2fs_should_use_dio(inode, iocb, from);
 
+	/* dio is not compatible w/ atomic write */
+	if (dio && f2fs_is_atomic_file(inode)) {
+		ret = -EOPNOTSUPP;
+		goto out_unlock;
+	}
+
 	/* Possibly preallocate the blocks for the write. */
 	target_size = iocb->ki_pos + iov_iter_count(from);
 	preallocated = f2fs_preallocate_blocks(iocb, from, dio);